Question

Here is the optimization problem for the soft-margin SVM. min w??^d, b??, ???^n ||w||^2 + C ?_{i=1}^n ?_i s.t.: y^{(i)}(w · x^{(i)} + b) ? 1 - ?_i for all i = 1, 2, ..., n ? ? 0 a) How many slack variables are there? The answer should be a function of n and/or d.

          Here is the optimization problem for the soft-margin SVM.

min w??^d, b??, ???^n ||w||^2 + C ?_{i=1}^n ?_i
s.t.: y^{(i)}(w · x^{(i)} + b) ? 1 - ?_i for all i = 1, 2, ..., n
? ? 0

a) How many slack variables are there? The answer should be a function of n and/or d.

Here is the optimization problem for the soft-margin SVM.

min w??^d, b??, ???^n ||w||^2 + C ?i=1^n ?i
s.t.: y^(i)(w · x^(i) + b) ? 1 - ?i for all i = 1, 2, ..., n
? ? 0

a) How many slack variables are there? The answer should be a function of n and/or d.

Added by Concepci-N M.

Calculus: Early Transcendentals

James Stewart 8th Edition

Instant Answer

Solved by Expert Suman Saurav Thakur

Step 1

The given optimization problem for the soft-margin SVM is: $$ \min_{w, b, \xi} \frac{1}{2} ||w||^2 + C \sum_{i=1}^n \xi_i $$ subject to the constraints: $$ Show more…

Show all steps

Thanks for your feedback!

Here is the optimization problem for the soft-margin SVM: Minimize ||w||^2 + C * Σξ Subject to y((w^T * x) + b) ≥ 1 - ξ ξ ≥ 0 where w is the weight vector, x is the input vector, b is the bias term, y is the class label, and C is a constant. How many slack variables are there? The answer should be a function of n and d.